DeepFolio: Convolutional Neural Networks for Portfolios with Limit Order Book Data
This work addresses portfolio optimization for financial traders and investors, offering incremental improvements over existing methods.
The paper tackles portfolio management using limit order book data by proposing DeepFolio, a convolutional neural network model that outperforms state-of-the-art methods on the FI-2010 benchmark and shows superior results in portfolio allocation for crypto-assets with rebalancing.
This work proposes DeepFolio, a new model for deep portfolio management based on data from limit order books (LOB). DeepFolio solves problems found in the state-of-the-art for LOB data to predict price movements. Our evaluation consists of two scenarios using a large dataset of millions of time series. The improvements deliver superior results both in cases of abundant as well as scarce data. The experiments show that DeepFolio outperforms the state-of-the-art on the benchmark FI-2010 LOB. Further, we use DeepFolio for optimal portfolio allocation of crypto-assets with rebalancing. For this purpose, we use two loss-functions - Sharpe ratio loss and minimum volatility risk. We show that DeepFolio outperforms widely used portfolio allocation techniques in the literature.